Message pushing method and device, electronic equipment and medium

Abstract

The invention provides a message pushing method and device, electronic equipment and a medium, and relates to the field of message pushing, and the method comprises the steps that a client processes attribute information and behavior characteristics of a user, and determines a static identifier and a dynamic identifier; the client determines a connection request with the server based on a target composite identifier formed by the static identifier and the dynamic identifier, and sends the connection request to the server; and the server determines a target message corresponding to the target composite identifier in the connection request based on the corresponding relationship between the configured different composite identifiers and different messages, so as to push the target message to the corresponding client according to the static identifier. According to the method, the dynamic identifier can be generated in combination with the user behavior and the equipment state, and the pushing individuation and accuracy are improved. And the client carries the dynamic identifier, so that the server can identify the state and the demand of the user in real time. And the server intelligently compares the target composite identifier to realize accurate directional pushing of the message.

Description

Technical Field

[0001] The present application relates to the field of message push, and more specifically, to a message push method, device, electronic device and medium. Background Art

[0002] SSE technology can push messages from the server to the client in real time, but its limitation is that it cannot achieve refined targeted push. Existing SSE technology lacks the ability to effectively distinguish clients, resulting in all clients receiving the same data stream, which cannot meet the needs of specific users or scenarios. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a message push method, device, electronic device and medium, which are used to solve the above-mentioned problems existing in the prior art and can accurately push messages according to the behavioral characteristics of different users.

[0004] In a first aspect, a message push method is provided, which is applied to a message push system including a client and a server. The method may include:

[0005] The client encrypts the attribute information of the user to obtain a static identifier;

[0006] The client processes the behavior characteristics corresponding to the multiple behavior information of the user to determine the dynamic identifier;

[0007] The client determines a connection request with a server based on a target composite identifier composed of the static identifier and the dynamic identifier, and sends the connection request to the server;

[0008] The server determines the target message corresponding to the target composite identifier in the connection request based on the configured correspondence between different composite identifiers and different messages, so as to push the target message to the corresponding client according to the static identifier.

[0009] In a possible implementation, the client processes the behavior features corresponding to the multiple behavior information of the user to determine the dynamic identifier, including:

[0010] Determining at least one target behavior feature among the behavior features corresponding to the plurality of behavior information;

[0011] Using the Kmeans algorithm, cluster at least one target behavior feature to determine the target label;

[0012] The dynamic identifier is generated according to the target tag.

[0013] In a possible implementation, determining at least one target behavior feature among multiple behavior features includes:

[0014] Classify multiple behavioral features to obtain behavioral features of different categories;

[0015] For any category of behavioral characteristics, the behavioral characteristics of the category are integrated to determine the category behavioral characteristics;

[0016] A decision tree is used to screen multiple categories of behavioral features and determine at least one target behavioral feature.

[0017] In a possible implementation, a decision tree is used to screen multiple categories of behavior features to determine at least one target behavior feature, including:

[0018] Calculate the behavioral features of multiple categories to determine the target entropy;

[0019] Calculate the behavioral characteristics of multiple categories separately to determine the Gini index;

[0020] For any category behavior feature, determining information gain based on the Gini index and the target entropy;

[0021] According to the configured preset information gain, a target information gain is determined among multiple information gains, and the category behavior feature corresponding to the target information gain is determined as the target behavior feature.

[0022] In a possible implementation, the multiple behavior characteristics include: purchase behavior characteristics, search behavior characteristics, and browsing behavior characteristics of the user at the client;

[0023] The purchasing behavior characteristics include: purchase frequency, type of purchased products and purchase time;

[0024] The browsing behavior characteristics include: the time of browsing pages and the types of browsed products;

[0025] The search behavior characteristics include: search keywords, search time period and search probability.

[0026] In a possible implementation, the structure of the connection request includes: a request line, a request header, and a request body;

[0027] The request header includes: the target server domain name, the target composite identifier, the type of data received by the client and the connection status.

[0028] In a possible implementation, the static identifier and the dynamic identifier in the target composite identifier are connected by a configured separator.

[0029] In a second aspect, a message push device is provided, which is applied to a message push system including a client and a server, and the device may include:

[0030] An encryption unit, used for the client to encrypt the attribute information of the user to obtain a static identifier;

[0031] A processing unit, used for the client to process the behavior characteristics corresponding to the multiple behavior information of the user and determine the dynamic identifier;

[0032] A determination unit, configured for the client to determine a connection request with a server based on a target composite identifier composed of the static identifier and the dynamic identifier;

[0033] A sending unit, configured for the client to send the connection request to the server;

[0034] The determination unit is also used for the server to determine the target message corresponding to the target composite identifier in the connection request based on the corresponding relationship between different composite identifiers and different messages configured, so as to push the target message to the corresponding client according to the static identifier.

[0035] In a third aspect, an electronic device is provided, the electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0036] Memory, used to store computer programs;

[0037] The processor is used to implement any method step described in the first aspect when executing the program stored in the memory.

[0038] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0039] The present application provides a message push method, which is applied to a message push system including a client and a server, and the method includes: the client encrypts the attribute information of the user to obtain a static identifier; the client processes the behavior characteristics corresponding to multiple behavior information of the user to determine the dynamic identifier; the client determines the connection request with the server based on the target composite identifier composed of the static identifier and the dynamic identifier, and sends the connection request to the server; the server determines the target message corresponding to the target composite identifier in the connection request based on the correspondence between different composite identifiers and different messages configured, so as to push the target message to the corresponding client according to the static identifier. The method can generate a dynamic identifier in combination with user behavior and device status, thereby improving the personalization and accuracy of the push. In addition, the client carries the dynamic identifier, so that the server can identify the user status and needs in real time. The server generates a customized message based on the localized attributes and the user's target composite identifier. The server intelligently compares the target composite identifier to achieve accurate and directional push of the message. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A system architecture diagram for a message push method provided in an embodiment of the present application;

[0042] Figure 2 A flowchart of a message push method provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of a message push device provided in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0046] A message push method provided in the embodiment of the present application can be applied to Figure 1In the system architecture shown in Figure 1 As shown, the system may include a server and a client. The server may be a physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0047] The client is used to obtain the user's attribute information and multiple behavior information, and process the attribute information and behavior information to determine the target composite identifier; determine a connection request to connect to the server based on the target composite identifier, and send the connection request to the server.

[0048] The server, based on the connection request, determines the target message.

[0049] SSE (Server-Sent Events) is a technology based on HTTP protocol to push messages from the server to the client. It uses the long connection feature of HTTP protocol to allow the server to push messages to the client in real time after the client establishes a persistent connection.

[0050] The client sends a GET (Connect) request containing specific HTTP header information to indicate that it can receive event stream data and disable event caching.

[0051] When the server responds, it returns an HTTP header with the event streaming type and encoding, using chunked transfer encoding to stream dynamically generated content.

[0052] The client can pass data to the server through the query parameters of the GET request and can close the connection using the close method.

[0053] SSE technology can push messages from the server to the client in real time, but its limitation is that it cannot achieve refined targeted push. Existing SSE technology lacks the ability to effectively distinguish clients, resulting in all clients receiving the same data stream, which cannot meet the needs of specific users or scenarios.

[0054] Therefore, the present application provides a message push method to solve the above-mentioned problems existing in the prior art, and can perform accurate message push according to the behavioral characteristics of different users.

[0055] The preferred embodiments of the present application are described below in conjunction with the drawings in the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments and features in the embodiments of the present application may be combined with each other if there is no conflict.

[0056] Figure 2 A flow chart of a message push method provided in an embodiment of the present application. The method is applied to Figure 1 The message push system shown includes a client and a server, and the method may include:

[0057] The message push system can be understood as a message push system based on SSE technology.

[0058] Step S210: The client processes the attribute information and behavior information corresponding to the user in the preset time period, and determines a target composite identifier composed of a static identifier and a dynamic identifier.

[0059] Specifically, A. The process of determining static identification:

[0060] The client collects the attribute information corresponding to the user in the preset time period, and then encrypts the attribute information to obtain a static identifier. This process can be understood as: collecting basic information of the user, including but not limited to username and password, email address, mobile phone number, name, gender, birthday, IP address, device information, etc. Combine the username, email address, mobile phone number, name, gender, birthday and other information. After that, use the hash algorithm (SHA-256) to encrypt the combined information such as username, email address, mobile phone number, etc., obtain the corresponding hash value, and determine the corresponding hash value as the static identifier. Store each user's unique static identifier in the database, and use the static identifier to identify and associate user data in scenarios such as user login and data association.

[0061] B. Determination process of dynamic identification:

[0062] Collect behavioral characteristics corresponding to multiple behavioral information corresponding to the user in a preset time period, including but not limited to purchase behavior characteristics, search behavior characteristics and browsing behavior characteristics.

[0063] Purchasing behavior characteristics include: purchase frequency, type of products purchased, and time of purchase;

[0064] Browsing behavior characteristics include: time spent browsing pages, types of products browsed, and browsing depth;

[0065] Search behavior characteristics include: search keywords, search time period and search probability.

[0066] It may also include: users’ likes, comments, and shares of the content, the time period, usage duration, and startup frequency of the user’s use of the client, etc.

[0067] Afterwards, multiple behavioral features are classified to obtain behavioral features of different categories;

[0068] For any category of behavioral characteristics, the behavioral characteristics of the category are integrated to determine the category behavioral characteristics; this process can be understood as: integrating the purchase behavior characteristics within a preset time period. The integration process can integrate the purchase frequency, type of purchased products and purchase time according to the configured weights to obtain a comprehensive purchase behavior characteristic (category behavior characteristic).

[0069] Through machine learning models, such as decision trees, the weights of each category behavior feature are determined by information gain, thereby determining at least one target behavior feature. This process can be understood as: calculating multiple category behavior features to determine the target entropy; calculating multiple category behavior features separately to determine the Gini index; for any category behavior feature, determining the information gain based on the Gini index and the target entropy; determining the target information gain from multiple information gains according to the configured preset information gain, and determining the category behavior feature corresponding to the target information gain as the target behavior feature.

[0070] In some embodiments, the steps of classifying multiple behavior features to obtain behavior features of different categories and integrating the behavior features of any category to determine the category behavior features may not be performed. That is, by using a machine learning model, such as a decision tree, the weight of each behavior feature is determined by information gain, thereby determining at least one target behavior feature.

[0071] Convert the target behavior features into numerical feature vectors. For example, users’ browsing, searching, purchasing, and other behaviors can be converted into numerical values ​​in a vector.

[0072] Using the Kmeans algorithm, the feature vectors corresponding to at least one target behavior feature are clustered to determine the target label; the process may include: using the K-means algorithm, the feature vectors corresponding to at least one target behavior feature are clustered into different groups, each group can represent a user behavior pattern. This behavior pattern is called a cluster. Users will be divided into K clusters, and each cluster will have indicators such as cluster center, cluster label, and sum of squared errors within the cluster. For example, a cluster may represent "electronic product enthusiasts" and another cluster may represent "fashion apparel buyers." Get the cluster label as the dynamic identifier of this user.

[0073] Generate dynamic identifiers based on target labels.

[0074] Afterwards, the static identifier and the dynamic identifier are connected using a specific separator to form a target composite identifier, which is used for subsequent dynamic connections by the user.

[0075] It should be noted that the current dynamic identification and static identification are for the current preset time period; however, the dynamic identification and static identification are not static and unchanging, but can be dynamically updated according to the user's behavior and environmental changes. For example, if the user changes the device or changes the preference settings within the current preset time period, the dynamic identification and static identification will be regenerated or updated to obtain a new target composite identification. Specifically, when the user's registration information changes, the static identification will regenerate the static identification based on the user's updated registration information. Generally speaking, since the frequency of changes in user registration information is relatively small, the frequency of changes in static identification will not be very large. As the dynamic identification continuously collects user behavior information, once a significant behavior change is detected, the update of the dynamic identification is triggered. For example, some specific events, such as the user's purchase behavior characteristics, search behavior characteristics, browsing behavior characteristics, etc., will trigger the immediate update of the dynamic identification.

[0076] Static IDs serve as unique identifiers for users, while dynamic IDs may be generated based on the user's current session or real-time behavior, such as the currently browsed product category or search keywords.

[0077] Step S220: The client determines a connection request with the server based on the target composite identifier, and sends the connection request to the server.

[0078] Specifically, when the client initializes the SSE connection, in addition to sending a standard HTTP GET request, it also sends an HTTP header containing a target composite identifier of static and dynamic identifiers.

[0079] In simple terms, the structure of a connection request includes: request line, request header, and request body;

[0080] The request header may include:

[0081] Host: The domain name and port (if it is a non-standard port) of the target server, that is, the domain name of the target server.

[0082] Accept: Specifies the media type that the client can receive. For this technology, SSE, it is set to text / event-stream, which is the type of data that the client receives.

[0083] Connection: keep-alive, which means the client wants to keep the connection open, that is, connected.

[0084] Cookie: Contains the authentication session cookie, if required.

[0085] totalID: target composite ID, including static ID and dynamic ID.

[0086] Furthermore, the static identifier and the dynamic identifier in the target composite identifier are connected by a configured separator.

[0087] It should be noted that each part in the request header is represented by a field.

[0088] In some embodiments, when the client needs to be able to update the identification, it resends the connection request or notifies the server to update the identification through some mechanism. Generally speaking, the client detects the user's purchase behavior, search behavior, browsing page residence time, etc., which will trigger the real-time update of the dynamic identification through the interface. The dynamic identification update is a process of continuously collecting user behavior data for analysis, continuously grouping user behaviors and generating cluster labels.

[0089] Step S230: The server determines the target message corresponding to the target composite identifier in the connection request based on the configured correspondence between different composite identifiers and different messages, so as to push the target message to the corresponding client according to the static identifier.

[0090] Specifically, after receiving the HTTP GET request, the server parses the static representation and the dynamic identifier, and classifies the client into different push groups or sessions according to these identifiers.

[0091] After receiving the HTTP GET request, the server will check the HTTP header of the request to find the target composite identifier containing the static identifier and the dynamic identifier. The server extracts the static identifier and the dynamic identifier values ​​from the target composite identifier field. The static identifier value is the hash value generated when the user registered and stored in the database. The server uses the extracted static identifier value as the query condition to query the database to match the corresponding user information.

[0092] The server extracts the value of the dynamic identifier from the target composite identifier field. This value is the result of user behavior clustering and represents the user's current behavior pattern.

[0093] Afterwards, the server uses the collected user behavior features to re-analyze the user's behavior patterns through the K-means algorithm, predict user needs, and intelligently manage the life cycle of the SSE connection accordingly.

[0094] In this way, by intelligently managing the connection between the server and the client, the server can reduce unnecessary resource consumption, such as closing connections that have been inactive for a long time, or dynamically adjusting the push frequency under high load.

[0095] Afterwards, the server selects or generates personalized push content (target message) from the database based on the user's cluster tag and the correspondence between different composite identifiers and different messages configured in the database. For example, if the dynamic identifier indicates that the user is browsing electronic products, the server can push relevant discount information.

[0096] In some embodiments, the server will intelligently select the best time to push the target message based on the user's behavior pattern and context information, for example, pushing relevant recommendations when the user browses to the bottom of a page.

[0097] After that, after the target message is pushed, the server will collect user feedback (such as click-through rate, purchase behavior, etc.) to further optimize the push algorithm and improve the relevance and effectiveness of the push.

[0098] The overall solution of this application is illustrated by example:

[0099] Suppose an online e-commerce platform needs to push localized promotional information to users in different regions. Traditional SSE technology cannot distinguish the region where the user is located, resulting in all users receiving the same promotional information, which is not only inefficient but also has a poor user experience.

[0100] During the user registration process, the system collects user attribute information, such as user name, email address, mobile phone number, etc.

[0101] The client generates a unique static identifier for the corresponding customer through a hash algorithm (such as SHA-256). The static identifier is stored in the database and associated with the user's account information.

[0102] The client collects user behavior information in real time, such as browsing history, search history, and device status, such as current time and network speed. Based on this data, a machine learning model and clustering algorithm (such as K-means) are used to generate dynamic identifiers. Dynamic identifiers reflect users' real-time behavior and preferences and are used to update and push personalized content in real time.

[0103] When a user opens a web page or application, the client sends an SSE connection request to the server. The HTTP header of this connection request contains a target identifier composed of the user's static identifier and dynamic identifier.

[0104] After receiving the connection request, the server parses the static identifier and dynamic identifier in the HTTP header. The server will classify the user into a specific push group (for example, based on region or user preference) based on the static identifier and dynamic identifier.

[0105] When there is new promotional information, the server will generate a target message based on the localized attributes of the information (such as regional restrictions). The target message contains the corresponding dynamic identifier to ensure that only the target user group receives the information.

[0106] The server will traverse all SSE connections and check whether the dynamic identifier of each connection matches the dynamic identifier in the message. Only when the identifiers match, the server will push the message to the client.

[0107] After the user's client receives the pushed target message, it displays corresponding localized promotional information based on the content of the target message, thereby providing a more personalized and timely user experience.

[0108] The system collects user feedback on pushed content, such as click-through rate, purchase behavior, etc. This data is used to further optimize the algorithm and improve the relevance and effectiveness of push notifications.

[0109] The present application provides a message push method, which is applied to a message push system including a client and a server, and the method includes: the client encrypts the attribute information of the user to obtain a static identifier; the client processes the behavior characteristics corresponding to multiple behavior information of the user to determine the dynamic identifier; the client determines the connection request with the server based on the target composite identifier composed of the static identifier and the dynamic identifier, and sends the connection request to the server; the server determines the target message corresponding to the target composite identifier in the connection request based on the correspondence between different composite identifiers and different messages configured, so as to push the target message to the corresponding client according to the static identifier. The method can generate a dynamic identifier in combination with user behavior and device status, thereby improving the personalization and accuracy of the push. In addition, the client carries the dynamic identifier, so that the server can identify the user status and needs in real time. The server generates a customized message based on the localized attributes and the user's target composite identifier. The server intelligently compares the target composite identifier to achieve accurate and directional push of the message.

[0110] Corresponding to the above method, the embodiment of the present application also provides a message push device, such as Figure 3 As shown, the device comprises:

[0111] An encryption unit 310 is used for the client to encrypt the attribute information of the user to obtain a static identifier;

[0112] A processing unit 320, configured for the client to process the behavior features corresponding to the plurality of behavior information of the user and determine a dynamic identifier;

[0113] A determination unit 330, configured for the client to determine a connection request with a server based on a target composite identifier composed of the static identifier and the dynamic identifier;

[0114] A sending unit 340, configured for the client to send the connection request to the server;

[0115] The determination unit 330 is also used for the server to determine the target message corresponding to the target composite identifier in the connection request based on the configured correspondence between different composite identifiers and different messages, so as to push the target message to the corresponding client according to the static identifier.

[0116] The functions of each functional unit of a message push device provided in the above embodiment of the present application can be realized through the above method steps. Therefore, the specific working process and beneficial effects of each unit in a message push device provided in the embodiment of the present application are not repeated here.

[0117] The present application also provides an electronic device, such as Figure 4 As shown, it includes a processor 410 , a communication interface 420 , a memory 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other via the communication bus 440 .

[0118] Memory 430, for storing computer programs;

[0119] The processor 410 is used to execute the program stored in the memory 430 to implement the following steps:

[0120] The client encrypts the attribute information of the user to obtain a static identifier;

[0121] The client processes the behavior characteristics corresponding to the multiple behavior information of the user to determine the dynamic identifier;

[0122] The client determines a connection request with a server based on a target composite identifier composed of the static identifier and the dynamic identifier, and sends the connection request to the server;

[0123] The server determines the target message corresponding to the target composite identifier in the connection request based on the configured correspondence between different composite identifiers and different messages, so as to push the target message to the corresponding client according to the static identifier.

[0124] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0125] The communication interface is used for communication between the above electronic device and other devices.

[0126] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0127] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0128] The implementation methods and beneficial effects of the components of the electronic device in the above embodiments to solve the problems can be seen in Figure 2 The various steps in the illustrated embodiment are implemented, therefore, the specific working process and beneficial effects of the electronic device provided by the embodiment of the present application are not repeated here.

[0129] In another embodiment provided in the present application, a computer-readable storage medium is provided, in which instructions are stored. When the computer-readable storage medium is executed on a computer, the computer executes a message pushing method described in any one of the above embodiments.

[0130] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute a message pushing method described in any one of the above embodiments.

[0131] Those skilled in the art will appreciate that the embodiments in the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt a complete hardware embodiment, a complete software embodiment, or a form of an embodiment combining software and hardware. Moreover, the present application may adopt a form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] Unless otherwise defined, the technical terms or scientific terms used in this application should be understood by people with ordinary skills in the field to which the present invention belongs. "First", "second" and similar words used in this application do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect", "couple" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0136] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the present application embodiments are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application embodiments.

[0137] Obviously, those skilled in the art can make various changes and modifications to the embodiments in the present application without departing from the spirit and scope of the embodiments in the present application. Thus, if these modifications and variations of the embodiments in the present application are within the scope of the embodiments in the present application and their equivalents, the embodiments in the present application are also intended to include these modifications and variations.

Claims

1. A message push method, characterized in that: Applied to a message push system including a client and a server, the method includes: The client encrypts the attribute information of the user to obtain a static identifier; The client processes the behavior characteristics corresponding to the multiple behavior information of the user to determine the dynamic identifier; The client determines a connection request with a server based on a target composite identifier composed of the static identifier and the dynamic identifier, and sends the connection request to the server; The server determines the target message corresponding to the target composite identifier in the connection request based on the configured correspondence between different composite identifiers and different messages, so as to push the target message to the corresponding client according to the static identifier.

2. The method according to claim 1, characterized in that The client processes the behavior features corresponding to the plurality of behavior information of the user to determine the dynamic identifier, including: Determining at least one target behavior feature among the behavior features corresponding to the plurality of behavior information; Using the Kmeans algorithm, cluster at least one target behavior feature to determine the target label; The dynamic identifier is generated according to the target tag.

3. The method according to claim 2, characterized in that Among the multiple behavior characteristics, at least one target behavior characteristic is determined, including: Classify multiple behavioral features to obtain behavioral features of different categories; For any category of behavioral characteristics, the behavioral characteristics of the category are integrated to determine the category behavioral characteristics; A decision tree is used to screen multiple categories of behavioral features and determine at least one target behavioral feature.

4. The method according to claim 3, characterized in that A decision tree is used to screen multiple categories of behavioral features and determine at least one target behavioral feature, including: Calculate the behavioral features of multiple categories to determine the target entropy; Calculate the behavioral characteristics of multiple categories separately to determine the Gini index; For any category behavior feature, determining information gain based on the Gini index and the target entropy; According to the configured preset information gain, a target information gain is determined among multiple information gains, and the category behavior feature corresponding to the target information gain is determined as the target behavior feature.

5. The method according to claim 1, characterized in that The multiple behavior characteristics include: the user's purchase behavior characteristics, search behavior characteristics and browsing behavior characteristics on the client; The purchasing behavior characteristics include: purchase frequency, type of purchased products and purchase time; The browsing behavior characteristics include: the time of browsing pages and the types of browsed products; The search behavior characteristics include: search keywords, search time period and search probability.

6. The method according to claim 1, characterized in that The structure of the connection request includes: a request line, a request header and a request body; The request header includes: the target server domain name, the target composite identifier, the type of data received by the client and the connection status.

7. The method according to claim 6, characterized in that The static identifier and the dynamic identifier in the target composite identifier are connected by a configured separator.

8. A message push device, characterized in that: Applicable to a message push system including a client and a server, the device includes: An encryption unit, used for the client to encrypt the attribute information of the user to obtain a static identifier; A processing unit, used for the client to process the behavior characteristics corresponding to the multiple behavior information of the user and determine the dynamic identifier; A determination unit, configured for the client to determine a connection request with a server based on a target composite identifier composed of the static identifier and the dynamic identifier; A sending unit, configured for the client to send the connection request to the server; The determination unit is also used for the server to determine the target message corresponding to the target composite identifier in the connection request based on the corresponding relationship between different composite identifiers and different messages configured, so as to push the target message to the corresponding client according to the static identifier.

9. An electronic device, characterized in that: The electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.

Images